Jacobian Granger Causal Neural Networks for Analysis of Stationary and Nonstationary Data
This provides a method for researchers analyzing time series data to uncover dependencies and information flow, particularly in nonstationary contexts, but it appears incremental as it builds on existing Granger causality techniques with neural network enhancements.
The authors tackled the problem of identifying Granger causal variables, time lags, and interaction signs in time series data by introducing JGC, a neural network-based approach using the Jacobian for variable importance, which performs consistently well compared to other methods and can handle nonstationary systems with changing causal structures over time.
Granger causality is a commonly used method for uncovering information flow and dependencies in a time series. Here we introduce JGC (Jacobian Granger Causality), a neural network-based approach to Granger causality using the Jacobian as a measure of variable importance, and propose a thresholding procedure for inferring Granger causal variables using this measure. The resulting approach performs consistently well compared to other approaches in identifying Granger causal variables, the associated time lags, as well as interaction signs. Lastly, through the inclusion of a time variable, we show that this approach is able to learn the temporal dependencies for nonstationary systems whose Granger causal structures change in time.